Multimodal motion planning framework for autonomous driving vehicles

A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:

• receiving driving environment data of an autonomous vehicle, wherein the environment data includes a route segment;
• segmenting the route segment into a plurality of route sub-segments;
• assigning a specific driving scenario to each of the plurality of route sub-segments, wherein each specific driving scenario is included in a set of driving scenarios;
• assigning a first motion planning algorithm according to a first assigned driving scenario included in the set of driving scenarios;
• invoking the first motion planning algorithm to generate a first set of trajectories;
• and
• controlling the autonomous vehicle based on the first set of trajectories.

A data processing system, comprising:

• a processor;
• and
• a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including
• receiving driving environment data of an autonomous vehicle, wherein the environment data includes a route segment;
• segmenting the route segment into a plurality of route sub-segments;
• assigning a specific driving scenario to each of the plurality of route sub-segments, wherein each specific driving scenario is included in a set of driving scenarios;
• assigning a first motion planning algorithm according to a first assigned driving scenario included in the set of driving scenarios;
• invoking the first motion planning algorithm to generate a first set of trajectories;
• and
• controlling the autonomous vehicle based on the first set of trajectories.